# UGCFast.ai — robots.txt
# Last updated: 2026-04-24 (AEO-optimized + Content Signals per IETF draft)

# ─────────────────────────────────────────────────────────────
# Content Signals (contentsignals.org — IETF draft)
# Declares AI content usage preferences for all crawlers:
#   search=yes   → allow AI search engines to index + cite our pages
#   ai-input=yes → allow RAG / real-time AI answer systems to read us
#   ai-train=no  → disallow using our content for model training
# ─────────────────────────────────────────────────────────────
Content-Signal: search=yes, ai-input=yes, ai-train=no

# ─────────────────────────────────────────────────────────────
# Default rule — allow all standard search crawlers
# IMPORTANT: Do NOT Disallow /_next/ — Google/Bing need /_next/static/
# (CSS, JS chunks) to render pages for Mobile-Friendly + Core Web Vitals.
# Only block /_next/data/ (private RSC payload).
# ─────────────────────────────────────────────────────────────
User-agent: *
Allow: /
Disallow: /api/
Disallow: /account
Disallow: /dashboard
Disallow: /admin
Disallow: /_next/data/

# ─────────────────────────────────────────────────────────────
# AI / LLM crawlers — explicitly ALLOW for AEO discovery
# Being indexed by these = being recommended in AI answers
# ─────────────────────────────────────────────────────────────

# OpenAI (ChatGPT search + training)
User-agent: GPTBot
Allow: /
Disallow: /api/
Disallow: /account

User-agent: OAI-SearchBot
Allow: /
Disallow: /api/

User-agent: ChatGPT-User
Allow: /

# Anthropic (Claude search + training)
User-agent: ClaudeBot
Allow: /
Disallow: /api/

User-agent: anthropic-ai
Allow: /

User-agent: Claude-Web
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /
Disallow: /api/

User-agent: Perplexity-User
Allow: /

# Google AI (Gemini, AI Overviews — separate from Googlebot)
User-agent: Google-Extended
Allow: /

User-agent: GoogleOther
Allow: /

# Bing AI / Copilot
User-agent: bingbot
Allow: /

# Apple Intelligence
User-agent: Applebot-Extended
Allow: /

User-agent: Applebot
Allow: /

# Common Crawl (used by many LLM training pipelines)
User-agent: CCBot
Allow: /

# Mistral
User-agent: MistralAI-User
Allow: /

# Cohere
User-agent: cohere-ai
Allow: /

User-agent: cohere-training-data-crawler
Allow: /

# Meta AI
User-agent: FacebookBot
Allow: /

User-agent: Meta-ExternalAgent
Allow: /

# DuckDuckGo
User-agent: DuckAssistBot
Allow: /

# YouBot (You.com)
User-agent: YouBot
Allow: /

# Diffbot (used by enterprise AI)
User-agent: Diffbot
Allow: /

# ─────────────────────────────────────────────────────────────
# Sitemap & LLM discovery files
# ─────────────────────────────────────────────────────────────
Sitemap: https://ugcfast.ai/sitemap.xml

# AI-friendly content map (LLM crawlers look for these)
# https://ugcfast.ai/llms.txt
# https://ugcfast.ai/llms-full.txt